ClawHub
Back to skill

Security audit

Agent Paddleocr Vision

Security checks for vulnerabilities and agentic risk

Overview

This skill is a PaddleOCR cloud document-OCR guide that is coherent with its purpose, but users should understand that processed documents are sent to a third-party OCR service.

Install only if you are comfortable sending selected documents to a PaddleOCR cloud endpoint under your own token. Avoid using it on highly sensitive identity, financial, legal, or tax documents unless you understand the provider's retention, logging, and privacy terms; also note that this package did not include the referenced scripts or requirements files for local review.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

md
Required environment variables:
- `PADDLEOCR_DOC_PARSING_API_URL` — API endpoint ending in `/layout-parsing`
- `PADDLEOCR_ACCESS_TOKEN` — Access token

Optional:
- `PADDLEOCR_DOC_PARSING_TIMEOUT` — Default 600 seconds

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill clearly sends user-provided documents to a remote PaddleOCR cloud API, but the top-level description and quick-start flow do not prominently warn users that document contents leave the local environment. This can lead to accidental disclosure of sensitive personal, financial, legal, or identity documents to a third party without informed consent, which is especially risky given the supported document types include passports, ID cards, contracts, and bank statements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.